{"title":"Physics-Informed DeepMRI: k-Space Interpolation Meets Heat Diffusion","authors":"Zhuo-Xu Cui;Congcong Liu;Xiaohong Fan;Chentao Cao;Jing Cheng;Qingyong Zhu;Yuanyuan Liu;Sen Jia;Haifeng Wang;Yanjie Zhu;Yihang Zhou;Jianping Zhang;Qiegen Liu;Dong Liang","doi":"10.1109/TMI.2024.3462988","DOIUrl":null,"url":null,"abstract":"Recently, diffusion models have shown considerable promise for MRI reconstruction. However, extensive experimentation has revealed that these models are prone to generating artifacts due to the inherent randomness involved in generating images from pure noise. To achieve more controlled image reconstruction, we reexamine the concept of interpolatable physical priors in k-space data, focusing specifically on the interpolation of high-frequency (HF) k-space data from low-frequency (LF) k-space data. Broadly, this insight drives a shift in the generation paradigm from random noise to a more deterministic approach grounded in the existing LF k-space data. Building on this, we first establish a relationship between the interpolation of HF k-space data from LF k-space data and the reverse heat diffusion process, providing a fundamental framework for designing diffusion models that generate missing HF data. To further improve reconstruction accuracy, we integrate a traditional physics-informed k-space interpolation model into our diffusion framework as a data fidelity term. Experimental validation using publicly available datasets demonstrates that our approach significantly surpasses traditional k-space interpolation methods, deep learning-based k-space interpolation techniques, and conventional diffusion models, particularly in HF regions. Finally, we assess the generalization performance of our model across various out-of-distribution datasets. Our code are available at \n<uri>https://github.com/ZhuoxuCui/Heat-Diffusion</uri>\n.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on medical imaging","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10683732/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Recently, diffusion models have shown considerable promise for MRI reconstruction. However, extensive experimentation has revealed that these models are prone to generating artifacts due to the inherent randomness involved in generating images from pure noise. To achieve more controlled image reconstruction, we reexamine the concept of interpolatable physical priors in k-space data, focusing specifically on the interpolation of high-frequency (HF) k-space data from low-frequency (LF) k-space data. Broadly, this insight drives a shift in the generation paradigm from random noise to a more deterministic approach grounded in the existing LF k-space data. Building on this, we first establish a relationship between the interpolation of HF k-space data from LF k-space data and the reverse heat diffusion process, providing a fundamental framework for designing diffusion models that generate missing HF data. To further improve reconstruction accuracy, we integrate a traditional physics-informed k-space interpolation model into our diffusion framework as a data fidelity term. Experimental validation using publicly available datasets demonstrates that our approach significantly surpasses traditional k-space interpolation methods, deep learning-based k-space interpolation techniques, and conventional diffusion models, particularly in HF regions. Finally, we assess the generalization performance of our model across various out-of-distribution datasets. Our code are available at
https://github.com/ZhuoxuCui/Heat-Diffusion
.
最近,弥散模型在核磁共振成像重建方面显示出了相当大的前景。然而,大量实验表明,由于从纯噪声生成图像的固有随机性,这些模型容易产生伪影。为了实现更可控的图像重建,我们重新审视了 k 空间数据中可插值物理先验的概念,特别关注从低频 k 空间数据插值高频 k 空间数据。从广义上讲,这种洞察力促使生成范式从随机噪声转向以现有低频 k 空间数据为基础的更具确定性的方法。在此基础上,我们首先建立了从低频 k 空间数据插值高频 k 空间数据与反向热扩散过程之间的关系,为设计生成缺失高频数据的扩散模型提供了一个基本框架。为了进一步提高重建精度,我们将传统的物理信息 k 空间插值模型作为数据保真度项整合到我们的扩散框架中。使用公开数据集进行的实验验证表明,我们的方法明显优于传统的 k 空间插值方法、基于深度学习的 k 空间插值技术和传统的扩散模型,尤其是在高频区域。最后,我们评估了我们的模型在各种分布外数据集上的泛化性能。我们的代码见 https://github.com/ZhuoxuCui/Heat-Diffusion。